Conference Secretary at:
1st floor of Physics and Mathematics
School.
Section of Electronics & Computers.
Tel.: + 30 2310 998071


 

MOCAST is Technically Sponsored by:

IEEE Logo


 

 

Keynote Speeches:

 

 

The next step in heterogeneous computing: Near-memory and in-memory computing

       by Prof. Dietmar Fey,   University Erlangen-Nuremberg, Germany

  

 

Abstract

The most driving force in designing new processor and computer architectures in the last two decades was the necessity to save the energy consumption in the circuits needed for processing, storing and transporting data. More and more powerful embedded devices as well as manageable HPC systems could satisfy the demand for more compute performance only since they reduced drastically their energy consumption. This process brought us the development from single-core to multi/many-core and heterogeneous architectures and it is necessary that this process has to continue.

And this next step will bring us the realisation of new concepts for a closer co-operation of processing and storage what is denoted as near-memory processing and in-memory processing. This new kind of processing or better to say pre-processing is the consequence of the fact that it costs sometimes more energy to move data from storage to processor than to process it directly on that location where the data is, either in the memory or close to a data capturing sensor. The last scenario corresponds to that what is denoted as edge computing in literature.

The emerging of new memristive devices like e.g. ReRAMs, PCRAMs or STT-MRAMs, which can not only store data energy-efficient but also process it supports decisively the design and future realisation of new energy-aware near-and in-memory computing architectures. Besides, they offer also new qualitative benefits compared to conventional SRAM and DRAM technologies like the storage of multiple states in one physical memory cell.  The keynote will present a generic overview of the development towards near- and in memory computing concepts as well as an evaluation of concepts for Boolean data processing with memristive devices. In addition, results achieved in the lab of the speaker for energy-efficient non-volatile flip-flops as well as ternary compute units are discussed as a possibility on the way to energy-saving near-memory and in-memory computing architectures.  

 

Short CV:  Prof. Dr.-Ing. Dietmar Fey holds a diploma degree in Computer Science from Friedrich-Alexander-University (FAU) Erlangen-Nürnberg, Germany.  In 1992 he received a Ph.D. from FAU with a work on an investigation about Using Optics in Computer Architectures. From 1994 to 1999 he researched at Friedrich-Schiller-University Jena where he made his habilitation. From 1999 to 2001 he worked as lecturer at University Siegen before he became a Professor for Computer Engineering at University Jena. Since 2009 he leads the Chair for Computer Architecture at FAU Erlangen-Nürnberg.

Prof. Fey was involved in several national and international research projects and initiatives on parallel and embedded computing. He participated in the nationwide priority Program “SPP 1188 Organic Computing” funded by German Research Foundation (Deutsche Forschungsgemeinschaft DFG) and in the DFG-funded Ph.D. student elite Research Training Group on “Heterogeneous Image Systems”. Furthermore he was involved in the project “Interchip Optical Communications and Photonic PCBs for next generation OBP” funded by ESA and in joint projects with industrial partners on Grid and Cloud Computing technology (Optinum Grid, part of the German D-Grid community, and Cloud4Eng, part of the nationwide program Trusted Cloud). Currently he is a member of the H2020 project AllScale working on new C++ based parallel programming concepts for heterogeneous architectures.  He has published over 115 conference papers articles, 3 books, and about 100 papers in journals and reports. He is a member of HiPEAC (European Network of Excellence on High Performance and Embedded Architecture and Compilation) and a contributor of the HiPEAC roadmap, author of the Eurolab4HPC report “Disruptive Technologies for years 2020-2030”, and he is a member of the EU Cost Action 1401 “Memristors Devices, Models, Circuits, Systems and Applications”.

His research interests are in parallel computer architectures, parallel programming environments, parallel embedded systems, and memristive computing.

 

 

-----------------------------------------------------------------------------------------------------------------------------------------------------------------

 

 

Dealing with Complexity in Synthesizing System and Devices for Communication/Sensing Systems:The System-by-Design Paradigm

      by Prof. Andrea Massa, IEEE Fellow, University of Trento, Trento, Italy

 

 

 

Abstract
Synthesizing modern devices and systems for Communications and Sensing is mainly concerned with the solution of high-complexity problems, where the term complexity stands for large scale and/ or strong nonlinearity and/or ill-posedness. Moreover, the focus of the research in the design of complex systems has recently shifted from ad-hoc strategies based on the designer experience to automated iterative search methods thanks to the availability of huge computational resources and by the existence of efficient simulation tools that reliably evaluate the “quality” of the guess design. Nevertheless, several synthesis problems still remain computationally intractable (i.e., their optimization through iterative procedures requires months/years). However, such a class of problems is becoming more and more important because of increasing demand for advanced systems operating across different scales (e.g., combining nano- to macro-scale). The SbD is “a functional ecosystem to handle complexity in the design of large systems” and it consists in a guideline for the task‐oriented design, definition, and integration of system components to yield devices/systems with user‐desired performance having the minimum costs, the maximum scalability, and suitable reconfigurability properties. More specifically, it addresses three fundamental issues. Firstly, the identification of the solution descriptors that represents a formulation challenge. Indeed, a proper choice must guarantee a large flexibility for the potential solution (e.g., in terms of geometry and features of each sub‐system) without yielding to huge search spaces, which can become practically unmanageable for any search strategy. Secondly, the evaluation of the system/device response of the iteratively identified guess solutions in an accurate and fast way represents a modeling challenge. The assessment of the effectiveness/quality of a guess design (e.g., in terms of a suitable “cost function”), which is the fundamental information required by any synthesis procedure, should be done efficiently to enable the adoption of automatic iterative search techniques. Thirdly, the choice of the search methodology, which represents an exploration challenge. Actually, the solution‐space sampling should find the “best solution” descriptors (i.e., the global optimum of the problem) whatever the complexity of the cost function at hand. Unfortunately, no general purpose approach exists to address these issues and sub‐optimal strategies are often adopted in practice.As a result, the SbD guideline is that of defining, through a suitable formulation/re‐formulation of the complex synthesis problem at hand, a suitable “environment” for global optimization in which new or re‐customized evolutionary optimization tools can perform in a time‐effective and reliable way.In order to assess the effectiveness and the reliability of the SbD, several different electromagnetic engineering applications will be addressed as benchmark examples ranging from large radome profiling, complex radar systems, 2D and 3D metamaterial‐enhanced devices, as well as other field manipulating devices (wave absorbers, beam benders, polarizers, cloaks, etc.) with potentials at microwave, Terahertz, and optical frequencies. Of course, the intrinsic multi‐disciplinary nature and the generalityof the SbD framework also enable its further exploitations in contiguous engineering areas (including acoustics, mechanics, and civil engineering).

 

Short CV: Andrea Massa (IEEE Fellow, IET Fellow, Electromagnetic Academy Fellow) received the “laurea” degree in Electronic Engineering from the University of Genoa, Genoa, Italy, in 1992 and Ph.D. degree in EECS from the same university in 1996. From 1997 to 1999, he was an Assistant Professor of Electromagnetic Fields at the Department of Biophysical and Electronic Engineering (University of Genoa). From 2001 to 2004, he was an Associate Professor at the University of Trento. Since 2005, he has been a Full Professor of Electromagnetic Fields at the University of Trento, where he currently teaches electromagnetic fields, inverse scattering techniques, antennas and wireless communications, wireless services and devices, and optimization techniques.

At present, Prof. Massa is the director of the network of federated laboratories “ELEDIA Research Center” [ELEDIA@UTB in Bandar Seri Begawan (Brunei), ELEDIA@UESTC in Chengdu (China), ELEDIA@USIL in Lima (Perù), ELEDIA@UniNAGA in Nagasaki (Japan), ELEDIA@L2S in Paris (France), ELEDIA@CTU in Prague (Czech), ELEDIA@UniTN in Trento (Italy), ELEDIA@TSINGHUA in Beijing (China), ELEDIA@Innov'COM in Tunis (Tunisia)]. Moreover, he is Adjunct Professor at Penn State University (USA), Professor @ CentraleSupélec (France), and UC3M-Santander Chair of Excellence at the Universidad Carlos III de Madrid (Spain). He has been holder of a Senior DIGITEO Chair at L2S-CentraleSupélec and CEA LIST in Saclay (France), Visiting Professor at the Missouri University of Science and Technology (USA), the Nagasaki University (Japan), the University of Paris Sud (France), the Kumamoto University (Japan), and the National University of Singapore (Singapore). It has been appointed IEEE AP-S Distinguished Lecturer (2016-2018).

Prof. Massa serves as Associate Editor of the “IEEE Transaction on Antennas and Propagation” and Associate Editor of the “International Journal of Microwave and Wireless Technologies” and he is member of the Editorial Board of the “Journal of Electromagnetic Waves and Applications”, a permanent member of the “PIERS Technical Committee” and of the “EuMW Technical Committee”, and a ESoA member. He has been appointed in the Scientific Board of the “Società Italiana di Elettromagnetismo (SIEm)” and elected in the Scientific Board of the Interuniversity National Center for Telecommunications (CNIT). He has been appointed in 2011 by the National Agency for the Evaluation of the University System and National Research (ANVUR) as a member of the Recognized Expert Evaluation Group (Area 09, ‘Industrial and Information Engineering’) for the evaluation of the researches at the Italian University and Research Center for the period 2004-2010. Furthermore, he has been elected as the Italian Member of the Management Committee of the COST Action TU1208 “Civil Engineering Applications of Ground Penetrating Radar”.

His research activities are mainly concerned with inverse problems, analysis/synthesis of antenna systems and large arrays, radar systems synthesis and signal processing, crosslayer optimization and planning of wireless/RF systems, semantic wireless technologies, system-by-design and materialbydesign (metamaterials and reconfigurablematerials), and theory/applications of optimization techniques to engineering problems (tele-communications, medicine, and biology).

Prof. Massa published more than 600 scientific publications (partial list available at: http://eledia.science.unitn.it/index.php/ricerca/pubblicazioni) among which about 300 on international journals and more than 450 in international conferences where he presented more than 150 invited contributions. He has organized more than 70 scientific sessions in international conferences and has participated to several technological projects in the European framework (20 EU Projects) as well as at the national and local level with national agencies (more than 150 Projects/Grants).